spark2.x由浅入深深到底系列六之RDD java api详解四

SparkConf conf = new SparkConf().setAppName("appName").setMaster("local");
JavaSparkContext sc = new JavaSparkContext(conf);

JavaPairRDD<Integer, Integer> javaPairRDD =
sc.parallelizePairs(Arrays.asList(new Tuple2<>(1, 2),
new Tuple2<>(3, 4), new Tuple2<>(3, 6), new Tuple2<>(5, 6)));
JavaPairRDD<Integer, Integer> otherJavaPairRDD =
sc.parallelizePairs(Arrays.asList(new Tuple2<>(3, 9),
new Tuple2<>(4, 5)));
//结果： [(4,([],[5])), (1,([2],[])), (3,([4, 6],[9])), (5,([6],[]))]
System.out.println(javaPairRDD.cogroup(otherJavaPairRDD).collect());

//结果： [(4,([],[5])), (1,([2],[])), (3,([4, 6],[9])), (5,([6],[]))]
// groupWith和cogroup效果是一模一样的
System.out.println(javaPairRDD.groupWith(otherJavaPairRDD).collect());

//结果： [(3,(4,9)), (3,(6,9))]
//基于cogroup实现的，就是取cogroup结果中相同key在两个RDD都有value的数据
System.out.println(javaPairRDD.join(otherJavaPairRDD).collect());

//结果： [(1,(2,Optional.empty)), (3,(4,Optional[9])), (3,(6,Optional[9])), (5,(6,Optional.empty))]
//基于cogroup实现的，结果需要出现的key以左边的RDD为准
System.out.println(javaPairRDD.leftOuterJoin(otherJavaPairRDD).collect());

//结果： [(4,(Optional.empty,5)), (3,(Optional[4],9)), (3,(Optional[6],9))]
//基于cogroup实现的，结果需要出现的key以右边的RDD为准
System.out.println(javaPairRDD.rightOuterJoin(otherJavaPairRDD).collect());

//结果： [(4,(Optional.empty,Optional[5])), (1,(Optional[2],Optional.empty)), (3,(Optional[4],Optional[9])), (3,(Optional[6],Optional[9])), (5,(Optional[6],Optional.empty))]
//基于cogroup实现的，结果需要出现的key是两个RDD中所有的key
System.out.println(javaPairRDD.fullOuterJoin(otherJavaPairRDD).collect());